QA-VLM: Providing human-interpretable quality assessment for wire-feed laser additive manufacturing parts with Vision Language Models

TL;DR

This paper introduces QA-VLM, a vision-language model framework that provides human-interpretable quality assessments for laser additive manufacturing parts, enhancing trustworthiness and consistency over existing methods.

Contribution

The paper presents a novel QA-VLM framework that integrates application-specific knowledge into vision-language models for interpretable quality assessment in additive manufacturing.

Findings

Higher validity and consistency in explanations compared to off-the-shelf VLMs.

Effective application of VLMs for interpretability in AM quality assessment.

Demonstrated on 24 laser wire DED-LW samples.

Abstract

Image-based quality assessment (QA) in additive manufacturing (AM) often relies heavily on the expertise and constant attention of skilled human operators. While machine learning and deep learning methods have been introduced to assist in this task, they typically provide black-box outputs without interpretable justifications, limiting their trust and adoption in real-world settings. In this work, we introduce a novel QA-VLM framework that leverages the attention mechanisms and reasoning capabilities of vision-language models (VLMs), enriched with application-specific knowledge distilled from peer-reviewed journal articles, to generate human-interpretable quality assessments. Evaluated on 24 single-bead samples produced by laser wire direct energy deposition (DED-LW), our framework demonstrates higher validity and consistency in explanation quality than off-the-shelf VLMs. These results highlight the potential of our approach to enable trustworthy, interpretable quality assessment in AM applications.